© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 18-TRANSCODER-HP
    4. 89555
    Prev
    Next
    INDEX
    Explanations

    Code/formatting identifier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     writers
    -0.25
    .addCell
    -0.25
    éĩį建
    -0.25
    ën
    -0.24
    桨
    -0.24
    à´¸
    -0.23
    æĮĽ
    -0.23
    OMP
    -0.23
    Ent
    -0.23
    æĮİ
    -0.23
    POSITIVE LOGITS
    æłĩåĩĨåĮĸ
    0.32
    pite
    0.28
    Wo
    0.26
    oine
    0.26
    å¿ĥçIJĨåѦ
    0.26
    .mozilla
    0.26
    满äºĨ
    0.25
    满
    0.25
     standardized
    0.25
    Ruby
    0.24
    Activations Density 14.100%

    No Known Activations